Skip to content

Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 9 papers
Filter5

Attack type

Poisoning and backdoors5Detection evasion3

Attack technique

Defense-targeted9Dormant triggers16

Impact

Harmful content3

System type

Models and APIs9coding agent0web agent0

Attack surface / entry point

Training data7Weights and gradients4

Layer

Prompt layer8Model layer7Application layer6Training and data layer9

System component

Guardrails and judges3Fine-tuning and open weights7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack technique：Defense-targetedSystem type：Models and APIsSystem type：coding agentSystem type：web agentLayer：Training and data layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.07723

    Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

    提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答

    arXiv
    2610.07723
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4

    Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.27124

    Fed-ADR：用恶意编排服务器协同客户端梯度操纵攻击联邦学习

    提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复

    arXiv
    2609.27124
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    CNN（MNIST：2 Conv + 3 FC）, CNN（Fashion-MNIST：6 Conv + 1 FC）, ResNet18（CIFAR-10）
    AbstractFed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。

    Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。

    Paper analysisRead analysis
  6. AttacksarXiv 2607.21839

    论文指出密码学模型认证的假设缺口：审计通过但部署失效

    提出数据伪造攻击，使密码学模型认证在审计集通过但部署失效

    arXiv
    2607.21839
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    SciKit-Learn decision tree, XGBoost, 226M-parameter neural network and others4
    Abstract固定审计集上的 ZKP 认证可被数据伪造绕过。

    这篇工作同时给出对 CMC 的数据伪造攻击，以及先承诺、后抽样的认证模板。。

    Paper analysisRead analysis
  8. AttacksarXiv 2601.14310

    CORVUS：用 LoRA 伪装内部信号绕过单次幻觉检测器

    提出 CORVUS，用 LoRA 伪装内部遥测以绕过幻觉检测器

    arXiv
    2601.14310
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Vicuna-7B (v1.5), Llama-3-8B-Instruct and others4

    Abstract作者称内部遥测在自适应模型侧对抗下易被操纵，CORVUS 通过轻量适配器微调降低了多种幻觉检测器的效果。

    Paper analysisRead analysis
You have reached the end